CN105574522A - Bill entry method and device - Google Patents
Bill entry method and device Download PDFInfo
- Publication number
- CN105574522A CN105574522A CN201410621412.7A CN201410621412A CN105574522A CN 105574522 A CN105574522 A CN 105574522A CN 201410621412 A CN201410621412 A CN 201410621412A CN 105574522 A CN105574522 A CN 105574522A
- Authority
- CN
- China
- Prior art keywords
- video data
- document
- data
- logged
- bills
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a bill entry method, which comprises the following steps of obtaining video data of a bill requiring data entry; recognizing the bill data from the video data; and storing the bill data. The invention also discloses a bill entry device. The method and the device provided by the invention realize an intelligent simple and convenient bill entry process; the accuracy and the efficiency of the bill entry are improved; and the security of the bill entry is ensured.
Description
Technical field
The present invention relates to bills data processing technology field, particularly relate to document input method and device.
Background technology
Enterprise needs ceaselessly to process documents different in a large number in the process of going concern, so that record, verification and management work.Due to all disunities such as document shape, form, traditional document typing often can only by the mode of artificial nucleus to manual typing, and this mode document Input Process is loaded down with trivial details, easily make mistakes, and inefficiency.
At present, along with the development of science and technology, the technology such as one-dimension code, Quick Response Code is widely applied to information and stores the fields such as transmission.The design of document also generally have employed this technology, makes the accuracy rate of document typing and efficiency have raising by scanning one-dimension code or Quick Response Code.But, although decrease artificial participation by the mode typing document of scanning one-dimension code, Quick Response Code, need to increase the operations such as artificial barcode scanning, cause the efficiency of document typing and accuracy lower, and cannot the security of guarantee document.
Foregoing, only for auxiliary understanding technical scheme of the present invention, does not represent and admits that foregoing is prior art.
Summary of the invention
Fundamental purpose of the present invention be to solve the efficiency of document typing and accuracy lower, and cannot the problem of security of guarantee document.
For achieving the above object, a kind of document input method provided by the invention, comprises the following steps:
Obtain the video data of document to be logged;
From described video data, identify bills data and preserve.
Preferably, described identify from described video data bills data and preserve step comprise:
Determine the recognition rule of video data and preserve rule;
From described video data, bills data is identified according to described recognition rule;
According to described preservation rule, identified bills data is preserved.
Preferably, when described recognition rule be recognition sequence and recognizer time, the described step identifying bills data according to described recognition rule from described video data comprises:
From described video data, video data to be identified is selected successively according to described recognition sequence;
From selected video data, bills data is identified successively according to described recognizer.
Preferably, identify from described video data bills data and preserve step comprise:
Judge whether described video data is current supported form;
When described video data is not for current supported form, described video data is converted to current supported form;
From the video data after conversion, identify bills data and preserve.
Preferably, described video data is obtained by camera, and the step of the video data of described acquisition document to be logged comprises:
Obtain the duration that camera takes a two field picture;
The shooting area that document to be logged enters described camera is successively controlled according to described duration;
Control the image that described camera takes the document to be logged entering described shooting area successively, the image photographed continuously by described camera is as the video data of document to be logged.
In addition, for achieving the above object, the present invention also provides a kind of document input device, comprising:
Acquisition module, for obtaining the video data of document to be logged;
Identification module, for identifying bills data from described video data;
Typing module, for preserving identified bills data.
Preferably, described identification module comprises determining unit and recognition unit,
Described determining unit, for determining the recognition rule of video data and preserving rule;
Described recognition unit, for identifying bills data according to described recognition rule from described video data;
Described typing module, also for being preserved by identified bills data according to described preservation rule.
Preferably, described recognition unit, also for selecting video data to be identified successively from described video data according to described recognition sequence; From selected video data, bills data is identified successively according to described recognizer.
Preferably, described document input device also comprises judge module, for judging whether described video data is current supported form;
Format converting module, for when described video data is not for current supported form, is converted to current supported form by described video data;
Described recognition unit, also for identifying bills data from the video data after conversion;
Described typing module, also for being preserved by identified bills data.
Preferably, described acquisition module comprises acquiring unit, takes the duration of a two field picture for obtaining camera;
Control module, for controlling according to described duration the shooting area that document to be logged enters described camera successively;
Control the image that described camera takes the document to be logged entering described shooting area successively;
Described acquiring unit, also for the image that photographed continuously by the described camera video data as document to be logged.
The present invention is by first taking into video data by document to be logged, identifying bills data from described video data and preserving, although effectively avoid decreasing artificial participation by the mode typing document of scanning one-dimension code, Quick Response Code, but need to increase the operations such as artificial barcode scanning, the efficiency of document typing and accuracy is caused to reduce, and cannot the problem of security of guarantee document, because whole document Input Process is without the need to artificial participation, make document Input Process more intelligent, easy, improve the accuracy and efficiency of document typing, ensure that the security of document typing.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the first embodiment of document input method of the present invention;
Fig. 2 is the refinement schematic flow sheet of step S10 in Fig. 1;
Fig. 3 is the refinement schematic flow sheet of step S20 in Fig. 1;
Fig. 4 is the refinement schematic flow sheet of step S22 in Fig. 3;
Fig. 5 is the schematic flow sheet of the second embodiment of document input method of the present invention;
Fig. 6 is the high-level schematic functional block diagram of the first embodiment of document input device of the present invention;
Fig. 7 is the refinement high-level schematic functional block diagram of acquisition module in Fig. 6;
Fig. 8 is the refinement high-level schematic functional block diagram of identification module in Fig. 6;
Fig. 9 is the high-level schematic functional block diagram of the second embodiment of document input device of the present invention.
The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
The primary solutions of the embodiment of the present invention is: the video data obtaining document to be logged; From described video data, identify bills data and preserve.By document to be logged is first taken into video data, identifying bills data from described video data and preserving, although effectively avoid decreasing artificial participation by the mode typing document of scanning one-dimension code, Quick Response Code, but need to increase the operations such as artificial barcode scanning, the efficiency of document typing and accuracy is caused to reduce, and cannot the problem of security of guarantee document, because whole document Input Process is without the need to artificial participation, make document Input Process more intelligent, easy, improve the accuracy and efficiency of document typing, ensure that the security of document typing.
Because existing document typing mode is mainly by the mode of surface sweeping one-dimension code or Quick Response Code, need to increase the operations such as artificial barcode scanning in Input Process, cause the efficiency of document typing and accuracy to reduce, and cannot the problem of security of guarantee document.
Based on above-mentioned existing document typing Problems existing, the invention provides a kind of document input method.
With reference to the schematic flow sheet that Fig. 1, Fig. 1 are the first embodiment of document input method of the present invention.
In one embodiment, described document input method comprises:
Step S10, obtains the video data of document to be logged;
The main body performing document input method of the present invention can be electric terminal, can be the application program (such as, document typing software etc.) that described electric terminal loads further.Described electric terminal can be server, high-definition monitoring equipment, mobile phone, notebook computer, pad etc. have camera function or have the electric terminal be connected with the devices communicating of camera function.Described electric terminal is preferably server in the present embodiment.
User is when needs carry out document typing operation, and open the document input function of described server, and control described server and enter document typing pattern, described server obtains the video data of document to be logged.
With reference to figure 2, the process of the video data of described acquisition document to be logged can comprise:
Step S11, determines that camera takes the duration of a two field picture; Described camera can be included by described server self, also can be the camera connected by wired or wireless mode, described server is after entering document typing pattern, open camera, and determine that described camera takes the duration of a two field picture, described duration generates according to the performance of described camera, such as, can be 20ms or 50ms etc.
Step S12, controls according to described duration the shooting area that document to be logged enters described camera successively; In order to improve the efficiency of document to be logged, preferably, described duration is set as that document to be logged enters the time interval of the shooting area of described camera by described server.Described server is when determining that described camera takes the duration of a two field picture, the shooting area that document to be logged enters described camera is successively controlled according to described duration, described device document to be logged being entered successively described camera is automated procedure, namely by automatic feeding apparatus, document to be logged can be sent into described shooting area one by one.Be understandable that: the time interval that document to be logged enters described shooting area can set according to the performance of described automatic feeding apparatus, but the described time interval must be greater than the duration that described camera takes a two field picture.
Step S13, controls the image that described camera takes the document to be logged entering described shooting area successively; The image photographed continuously by described camera is as the video data of document to be logged.
Described server is after the described document to be logged of control enters described shooting area successively, control the image that described camera takes the document to be logged entering described shooting area successively, using the video data of the image taken by described camera as document to be logged.Preferably, comprise the complete bills data of document to be logged in order to ensure the video data captured by described camera, described server, when there being document to be logged to enter described shooting area, determines that whether the position of described document to be logged is at predeterminated position.Described predeterminated position is the position that described camera can photograph whole described document to be logged, and namely camera can capture the position of the bills data recorded in whole document to be logged.If the position of described document to be logged is not at predeterminated position, then send information, adjust camera position to point out the user of document typing or adjust the position that document to be logged enters, can get the bills data described in described document to be logged more accurately more comprehensively; If the position of described document to be logged is at predeterminated position, then control the image entering the document to be logged of shooting area described in the shooting of described camera.
Be appreciated that and be: preset a time threshold, described time threshold can be 5s or 10s etc., described server is when the duration that described shooting area does not photograph document image to be logged exceedes described preset time threshold, judge that the video data capture acquisition process of current document to be logged terminates, and point out user's document typing of typing document to complete; When the duration that described shooting area does not photograph document image to be logged does not exceed described preset time threshold, continue to wait for that document to be logged enters described shooting area, and when there being document to be logged to enter described shooting area, control described camera shooting image.
In other embodiments of the present invention, also can also be: after the image having taken a document to be logged, send information, to point out next document to be logged to enter described shooting area, according to the information of having taken, control entering of document to be logged.
Step S20, identifies bills data and preserves from described video data.
Described server, after the video data getting document to be logged, identifies bills data and preserves from described video data.
With reference to figure 3, described identify from described video data bills data and preserve process can comprise:
Step S21, determines the recognition rule of video data and preserves rule;
Described recognition rule includes but not limited to document distinguishing rule, corrects rule and recognizer etc., described document distinguishing rule includes but not limited to recognition sequence, the order of form recognition, the color etc. of identification font of receipt field in video data, described correction rule comprises carries out associated core to also correcting to document article unit price, quantity and total value, and described recognizer comprises character recognition, Chinese Character Recognition, shape recognition etc.Described preservation rule can be the sequencing of document number of the sequencing of field typing, described document to be logged, or the coded sequence of described document to be logged.Described recognition rule and described preservation rule can need to arrange according to document typing in advance, such as, can arrange in advance recognition sequence, recognizer.
Step S22, identifies bills data according to described recognition rule from described video data;
Described server, after the recognition rule determining described video data and preservation rule, identifies bills data according to described recognition rule from described video data.
With reference to figure 4, when described recognition rule comprises recognition sequence and recognizer, describedly from described video data, identify bills data process according to described recognition rule and can comprise:
Step S221, selects video data to be identified successively according to described recognition sequence from described video data;
Step S222, identifies bills data from selected video data successively according to described recognizer.
Described recognition sequence comprises according to the recognition sequence of field, the sequencing of the odd numbers of document to be logged or the coded sequence identification of document to be logged, described server selects video data to be identified successively according to described recognition sequence from described video data, namely select the field needing to identify, and identify bills data according to the recognition sequence of field according to described recognizer.Preferably, described server can also be after identifying bills data, correct according to correcting the unit price of rule to the article in document, number of articles and total value, the unit price being about to the article identified is compared with the corresponding unit price that prestores, to judge whether the unit price of the article identified mates with the unit price that prestores, if do not mate, then the unit price of described article is revised as consistent with the unit price that prestores, or send information, select to point out document typing user to be as the criterion with that unit price, and determine to be as the criterion with that unit price according to the information of user feedback.
Step S23, preserves identified bills data according to described preservation rule.
Identified bills data, after identifying bills data, is preserved according to described preservation rule by described server, such as, preserves according to the typing order of field or the odd numbers sequencing of bills data, or according to the coded sequence preservation etc. of bills data.
Preferably, described server is first taken the document to be logged entering shooting area, the image comprising bills data is selected from the image of shooting, then will wherein with the image image-erasing that repeat of shooting, go out bills data from not deleted image recognition according to field typing along interrogating and preserve.
The embodiment of the present invention is by first taking into video data by document to be logged, identifying bills data from described video data and preserving, effectively avoid by scanning one-dimension code, although the mode typing document of Quick Response Code decreases artificial participation, but need to increase the operations such as artificial barcode scanning, the efficiency of document typing and accuracy is caused to reduce, and cannot the problem of security of guarantee document, because whole document Input Process is without the need to artificial participation, make document Input Process more intelligent, easy, improve the accuracy and efficiency of document typing, ensure that the security of document typing.
With reference to the schematic flow sheet that Fig. 5, Fig. 5 are the second embodiment of document input method of the present invention.Based on the first embodiment of above-mentioned document input method, described step S20 can comprise:
Step S24, judges whether described video data is current supported form;
Step S25, when described video data is not for current supported form, is converted to current supported form by described video data;
Step S26, identifies bills data and preserves from the video data after conversion.
Described server determines current supported video format, such as, can be AVI form or WMV form etc., after the video data getting document to be logged, described server judges whether described video data is current supported form, if when described video data is not for current supported form, described video data is converted to current supported form, from the video data after conversion, identifies bills data and preserve.The form that described current supported form is supported for recognition system, it not the form that operating system is supported, such as, the form of the video data obtained is generally the H264 form through overcompression, current supported form is AVI form, then described server by described video data from H264 compressed format decompress(ion), and the video data after decompress(ion) is converted to AVI form, described transfer process can be realized by video format converter, concrete transfer process is existing video format conversion process, does not repeat them here.Described server is when the form of described video data is consistent with the form that current system is supported, such as, the form of described video data is AVI form, the form that current system is supported is AVI form, then by after described video data decompress(ion), directly from described video data, identify bills data and preserve, without the need to carrying out the conversion operations of video format.
The embodiment of the present invention, by when getting video data, first judging that whether the form of described video data is consistent with the form that current system is supported, when inconsistent, described video data being converted to the form that current system is supported.Guarantee to recognize bills data from obtained video data, and then improve the efficiency of document typing.
Corresponding the present invention further provides a kind of document input device.
With reference to the high-level schematic functional block diagram that Fig. 6, Fig. 6 are the first embodiment of document input device of the present invention.
In one embodiment, described document input device comprises: acquisition module 10, identification module 20 and typing module 30.
Described acquisition module 10, for obtaining the video data of document to be logged;
Described document input device can be electric terminal, can be the application program (such as, document typing software etc.) that described electric terminal loads further.Described electric terminal can be server, high-definition monitoring equipment, mobile phone, notebook computer, pad etc. have camera function or have the electric terminal be connected with the devices communicating of camera function.Described electric terminal is preferably server in the present embodiment.
User is when needs carry out document typing operation, and open the document input function of described server, and control described server and enter document typing pattern, described acquisition module 10 obtains the video data of document to be logged.
With reference to figure 7, described acquisition module 10 comprises: acquiring unit 11 and control module 12,
Described acquiring unit 11, for determining that camera takes the duration of a two field picture; Described camera can be included by described server self, also can be the camera connected by wired or wireless mode, described acquiring unit 11 is after entering document typing pattern, open camera, and determine that described camera takes the duration of a two field picture, described duration generates according to the performance of described camera, such as, can be 20ms or 50ms etc.
Described control module 12, for controlling according to described duration the shooting area that document to be logged enters described camera successively; In order to improve the efficiency of document to be logged, preferably, described duration is set as that document to be logged enters the time interval of the shooting area of described camera by described control module 12.Described control module 12 is when determining that described camera takes the duration of a two field picture, the shooting area that document to be logged enters described camera is successively controlled according to described duration, described device document to be logged being entered successively described camera is automated procedure, namely by automatic feeding apparatus, document to be logged can be sent into described shooting area one by one.Be understandable that: the time interval that document to be logged enters described shooting area can set according to the performance of described automatic feeding apparatus, but the described time interval must be greater than the duration that described camera takes a two field picture.
Described control module 12, also takes the image of the document to be logged entering described shooting area successively for controlling described camera;
Described acquiring unit 11, also for the image that photographed continuously by the described camera video data as document to be logged.
Described control module 12 is after the described document to be logged of control enters described shooting area successively, control the image that described camera takes the document to be logged entering described shooting area successively, using the video data of the image taken by described camera as document to be logged.Preferably, comprise the complete bills data of document to be logged in order to ensure the video data captured by described camera, described control module 12, when there being document to be logged to enter described shooting area, determines that whether the position of described document to be logged is at predeterminated position.Described predeterminated position is the position that described camera can photograph whole described document to be logged, and namely camera can capture the position of the bills data recorded in whole document to be logged.If the position of described document to be logged is not at predeterminated position, then described control module 12 sends information, adjust camera position to point out the user of document typing or adjust the position that document to be logged enters, can get the bills data described in described document to be logged more accurately more comprehensively; If the position of described document to be logged is at predeterminated position, then described control module 12 controls the image entering the document to be logged of shooting area described in the shooting of described camera.
Be appreciated that and be: described control module 12 presets a time threshold, described time threshold can be 5s or 10s etc., described server is when the duration that described shooting area does not photograph document image to be logged exceedes described preset time threshold, described control module 12 judges that the video data capture acquisition process of current document to be logged terminates, and points out user's document typing of typing document to complete; When the duration that described shooting area does not photograph document image to be logged does not exceed described preset time threshold, described control module 12 continues to wait for that document to be logged enters described shooting area, and when there being document to be logged to enter described shooting area, control described camera shooting image.
In other embodiments of the present invention, also can also be: after the image having taken a document to be logged, send information enter described shooting area to point out next document to be logged, control module 12, according to the information of having taken, controls entering of document to be logged.
Described identification module 20, for identifying bills data from described video data;
Described typing module 30, for preserving identified bills data.
Described server, after the video data getting document to be logged, identifies bills data and preserves from described video data.
With reference to figure 8, described identification module comprises: determining unit 21 and recognition unit 22,
Described determining unit 21, for determining the recognition rule of video data and preserving rule;
Described recognition rule includes but not limited to document distinguishing rule, corrects rule and recognizer etc., described document distinguishing rule includes but not limited to recognition sequence, the order of form recognition, the color etc. of identification font of receipt field in video data, described correction rule comprises carries out associated core to also correcting to document article unit price, quantity and total value, and described recognizer comprises character recognition, Chinese Character Recognition, shape recognition etc.Described preservation rule can be the sequencing of document number of the sequencing of field typing, described document to be logged, or the coded sequence of described document to be logged.Described recognition rule and described preservation rule can need to arrange according to document typing in advance, such as, can arrange in advance recognition sequence, recognizer.
Described recognition unit 22, for identifying bills data according to described recognition rule from described video data;
Described recognition unit 22 is determined the recognition rule of described video data in described determining unit 21 and is preserved after rule, identifies bills data according to described recognition rule from described video data.
Further, when described recognition rule comprises recognition sequence and recognizer, described recognition unit 22, also for selecting video data to be identified successively from described video data according to described recognition sequence; Bills data is identified from selected video data successively according to described recognizer.
Described recognition sequence comprise field recognition sequence, according to the sequencing of the odd numbers of document to be logged or the coded sequence identification of document to be logged, described recognition unit 22 selects video data to be identified successively according to described recognition sequence from described video data, namely select the field needing to identify, and identify bills data according to the recognition sequence of field according to described recognizer.Preferably, described recognition unit 22 can also be after identifying bills data, correct according to correcting the unit price of rule to the article in document, number of articles and total value, the unit price being about to the article identified is compared with the corresponding unit price that prestores, to judge whether the unit price of the article identified mates with the unit price that prestores, if do not mate, then the unit price of described article is revised as consistent with the unit price that prestores, or send information, select to point out document typing user to be as the criterion with that unit price, and determine to be as the criterion with that unit price according to the information of user feedback.
Described preservation module 30, also for being preserved by identified bills data according to described preservation rule.
Described preservation module 30 is after identifying bills data, according to described preservation rule, identified bills data is preserved, such as, preserve according to the typing order of field or the odd numbers sequencing of bills data, or according to the coded sequence preservation etc. of bills data.
Preferably, acquisition module 10 is first taken the document to be logged entering shooting area, the image comprising bills data is selected from the image of shooting, the image-erasing that determining unit 21 will wherein repeat with the image of shooting, recognition unit 22 goes out bills data and passes through to preserve module 30 to preserve from not deleted image recognition along news according to field typing.
The embodiment of the present invention is by first taking into video data by document to be logged, identifying bills data from described video data and preserving, effectively avoid by scanning one-dimension code, although the mode typing document of Quick Response Code decreases artificial participation, but need to increase the operations such as artificial barcode scanning, the efficiency of document typing and accuracy is caused to reduce, and cannot the problem of security of guarantee document, because whole document Input Process is without the need to artificial participation, make document Input Process more intelligent, easy, improve the accuracy and efficiency of document typing, ensure that the security of document typing.
With reference to the high-level schematic functional block diagram that Fig. 9, Fig. 9 are the second embodiment of document input device of the present invention.Described document input device also comprises: judge module 40 and modular converter 50,
Described judge module 40, for judging whether described video data is current supported form;
Described modular converter 50, for when described video data is not for current supported form, is converted to current supported form by described video data;
Described recognition unit 22, also for identifying bills data from the video data after conversion;
Described preservation module 30, also for being preserved by identified bills data.
Described judge module 40 determines current supported video format, such as, can be AVI form or WMV form etc., after the video data getting document to be logged, described judge module 40 judges whether described video data is current supported form, if when described video data is not for current supported form, described video data is converted to current supported form by described modular converter 50, and described recognition unit 22 is identified bills data and preserved by typing module 30 from the video data after conversion.The form that described current supported form is supported for recognition system, it not the form that operating system is supported, such as, the form of the video data obtained is generally the H264 form through overcompression, current supported form is AVI form, then described modular converter 50 by described video data from H264 compressed format decompress(ion), and by the video data after decompress(ion), described transfer process can be realized by video format converter, concrete transfer process is existing video format conversion process, does not repeat them here.Described recognition unit 22 is when the form of described video data is consistent with the form that current system is supported, such as, the form of described video data is AVI form, the form that current system is supported is AVI form, then by after described video data decompress(ion), directly from described video data, identify bills data and preserved by typing module 30, without the need to carrying out the conversion operations of video format.
The embodiment of the present invention is by when acquisition module 10 gets video data, first judge that whether the form of described video data is consistent with the form that current system is supported by judge module 40, when inconsistent, described video data is converted to the form that current system is supported by modular converter 50.Guarantee to recognize bills data from obtained video data, and then improve the efficiency of document typing.
These are only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (10)
1. a document input method, is characterized in that, comprises the following steps:
Obtain the video data of document to be logged;
From described video data, identify bills data and preserve.
2. document input method as claimed in claim 1, is characterized in that, describedly from described video data, identifies bills data and the step of preserving comprises:
Determine the recognition rule of video data and preserve rule;
From described video data, bills data is identified according to described recognition rule;
According to described preservation rule, identified bills data is preserved.
3. document input method as claimed in claim 2, is characterized in that, when described recognition rule be recognition sequence and recognizer time, the described step identifying bills data according to described recognition rule from described video data comprises:
From described video data, video data to be identified is selected successively according to described recognition sequence;
From selected video data, bills data is identified successively according to described recognizer.
4. the document input method as described in any one of claims 1 to 3, is characterized in that, identify from described video data bills data and preserve step comprise:
Judge whether described video data is current supported form;
When described video data is not for current supported form, described video data is converted to the form that current system is supported;
From the video data after conversion, identify bills data and preserve.
5. the document input method as described in any one of claims 1 to 3, is characterized in that, described video data is obtained by camera, and the step of the video data of described acquisition document to be logged comprises:
Obtain the duration that camera takes a two field picture;
The shooting area that document to be logged enters described camera is successively controlled according to described duration;
Control the image that described camera takes the document to be logged entering described shooting area successively, the image photographed continuously by described camera is as the video data of document to be logged.
6. a document input device, is characterized in that, comprising:
Acquisition module, for obtaining the video data of document to be logged;
Identification module, for identifying bills data from described video data;
Typing module, for preserving identified bills data.
7. document input device as claimed in claim 6, it is characterized in that, described identification module comprises determining unit and recognition unit,
Described determining unit, for determining the recognition rule of video data and preserving rule;
Described recognition unit, for identifying bills data according to described recognition rule from described video data;
Described typing module, also for being preserved by identified bills data according to described preservation rule.
8. document input device as claimed in claim 7, is characterized in that, described recognition unit, also for selecting video data to be identified successively from described video data according to described recognition sequence; From selected video data, bills data is identified successively according to described recognizer.
9. document input device as claimed in claim 7, it is characterized in that, described document input device also comprises judge module, for judging whether described video data is current supported form;
Format converting module, for when described video data is not for current supported form, is converted to current supported form by described video data;
Described recognition unit, also for identifying bills data from the video data after conversion;
Described typing module, also for being preserved by identified bills data.
10. the document input device as described in any one of claim 6 to 9, is characterized in that, described acquisition module comprises acquiring unit, taking the duration of a two field picture for obtaining camera;
Control module, for controlling according to described duration the shooting area that document to be logged enters described camera successively;
Control the image that described camera takes the document to be logged entering described shooting area successively;
Described acquiring unit, also for the image that photographed continuously by the described camera video data as document to be logged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410621412.7A CN105574522A (en) | 2014-11-06 | 2014-11-06 | Bill entry method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410621412.7A CN105574522A (en) | 2014-11-06 | 2014-11-06 | Bill entry method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105574522A true CN105574522A (en) | 2016-05-11 |
Family
ID=55884630
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410621412.7A Pending CN105574522A (en) | 2014-11-06 | 2014-11-06 | Bill entry method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574522A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2287819B (en) * | 1994-03-25 | 1996-12-18 | Gist Limited | Automated forms processing |
| CN101184195A (en) * | 2007-12-25 | 2008-05-21 | 腾讯科技（深圳）有限公司 | Audio/video living broadcast system and method |
| CN202711171U (en) * | 2012-06-05 | 2013-01-30 | 内蒙古埃伊尔科工贸有限责任公司 | Automatic recognition type-in device for handwritten texts of document |
| CN103488999A (en) * | 2013-09-11 | 2014-01-01 | 东华大学 | Invoice data recording method |
-
2014
- 2014-11-06 CN CN201410621412.7A patent/CN105574522A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2287819B (en) * | 1994-03-25 | 1996-12-18 | Gist Limited | Automated forms processing |
| CN101184195A (en) * | 2007-12-25 | 2008-05-21 | 腾讯科技（深圳）有限公司 | Audio/video living broadcast system and method |
| CN202711171U (en) * | 2012-06-05 | 2013-01-30 | 内蒙古埃伊尔科工贸有限责任公司 | Automatic recognition type-in device for handwritten texts of document |
| CN103488999A (en) * | 2013-09-11 | 2014-01-01 | 东华大学 | Invoice data recording method |
Non-Patent Citations (1)
| Title |
|---|
| 周蔚吾: "《数字化公路应用技术手册》", 30 April 2009 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9641715B2 (en) | Information processing device, method, and medium | |
| EP3267365B1 (en) | Fingerprint recognition method and system capable of improving fingerprint recognition rate | |
| CN104360736A (en) | Gesture-based terminal control method and system | |
| CN104537389A (en) | Human face recognition method and terminal equipment | |
| CN108039173B (en) | Voice information input method, mobile terminal, system and readable storage medium | |
| CN102270292A (en) | Mobile terminal and decoding method thereof | |
| CN104506346A (en) | Method and device for equipment operation and maintenance | |
| CN110598562B (en) | Vehicle image acquisition guiding method and device | |
| CN110866443A (en) | Portrait storage method, face recognition equipment and storage medium | |
| CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
| CN110929555B (en) | Face recognition method and electronic device using same | |
| CN111339811A (en) | Image processing method, device, equipment and storage medium | |
| CN105787845A (en) | Liquid medicine tracing back system and method | |
| CN110400560B (en) | Data processing method and device, storage medium and electronic device | |
| CN111045529B (en) | Data input method, system and related equipment | |
| CN105574522A (en) | Bill entry method and device | |
| JP2015222556A (en) | Document system, processing method therefor, and program | |
| WO2019127892A1 (en) | Method for remotely photographing picture, electronic device and computer readable storage medium | |
| TW201222430A (en) | Method for detecting objects and a corresponding control computer | |
| CN109240745B (en) | Instruction distribution method and device | |
| US9817849B2 (en) | Image recognition method for offline and online synchronous operation | |
| WO2017020168A1 (en) | Fingerprint recognition method and device | |
| CN111489111B (en) | Logistics object management device, logistics object extraction method thereof and electronic equipment | |
| CN113298074B (en) | Image recognition method and device, computer readable storage medium and processor | |
| CN113128297A (en) | Equipment docking method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160511 |
|
| RJ01 | Rejection of invention patent application after publication |